Arrow Research search

Author name cluster

Wenming Ye

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

1 paper
1 author row

Possible papers

1

NeurIPS Conference 2025 Conference Paper

Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs

  • Yifan Shen
  • Yuanzhe Liu
  • Jingyuan Zhu
  • Xu Cao
  • Xiaofeng Zhang
  • Yixiao He
  • Wenming Ye
  • James Rehg

Current Vision-Language Models (VLMs) struggle with fine-grained spatial reasoning, particularly when multi-step logic and precise spatial alignment are required. In this work, we introduce SpatialReasoner-R1, a vision-language reasoning model designed to address these limitations. To construct high-quality supervision for spatial reasoning, we design a Multi-Model Monte Carlo Tree Search (M3CTS) method that generates diverse, logically consistent Long Chain-of-Thought (LongCoT) reasoning trajectories. In addition, we propose a fine-grained Direct Preference Optimization (fDPO) method that introduces segment-specific preference granularity for descriptive grounding and logical reasoning, guided by a spatial reward mechanism that evaluates candidate responses based on visual consistency, spatial grounding, and logical coherence. Experimental results demonstrate that fDPO achieves relative performance gains of 4. 1% and 9. 0% over standard DPO on spatial qualitative and quantitative tasks, respectively. SpatialReasoner-R1, trained with fDPO, sets a new SoTA on SpatialRGPT-Bench, outperforming the strongest baseline by 9. 4% in average accuracy, while maintaining competitive performance on general vision-language tasks.

v2026.09.13